Skills
Navigate
skills/hainrixz/claude-seo-ai/seo-images-media/Gen Agent Trust Hub

seo-images-media

Pass

Audited by Gen Agent Trust Hub on Jun 15, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill identifies an attack surface for indirect prompt injection by processing untrusted HTML data from external web pages to generate accessibility content.
  • Ingestion points: HTML content is ingested via raw_html and rendered_dom fields in SKILL.md.
  • Boundary markers: No specific delimiters or instructions are used to isolate untrusted data from agent instructions.
  • Capability inventory: The skill utilizes Bash, WebFetch, and file-writing capabilities via the fix command.
  • Sanitization: No explicit sanitization or filtering of external content is described before interpolation into the prompt.
  • [COMMAND_EXECUTION]: The skill uses the Bash tool and references a local script node scripts/parse-html.mjs to facilitate HTML parsing and finding verification.
  • [EXTERNAL_DOWNLOADS]: The skill employs WebFetch to retrieve page snapshots and inspect remote image assets for dimension verification.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 15, 2026, 08:09 PM
Security Audit — agent-trust-hub — seo-images-media